postgres-wizard

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and reference files. There are no scripts (.py, .js, .sh), binaries, or configuration files that execute code.
  • [COMMAND_EXECUTION] (SAFE): While the documentation includes shell commands (e.g., psql, pg_partman setup) and SQL statements, these are provided as static educational examples for the user to read and manually apply to their own environment. There is no automated execution logic.
  • [EXTERNAL_DOWNLOADS] (SAFE): No external URLs or remote resources are referenced for download or execution. All dependencies mentioned (like pg_partman or pgvector) are standard PostgreSQL extensions referenced for architectural guidance.
  • [PROMPT_INJECTION] (SAFE): The instructions in SKILL.md clearly define a professional role centered on PostgreSQL internals. No patterns were found that attempt to bypass AI safety filters or exfiltrate system prompts.
  • [DATA_EXFILTRATION] (SAFE): The skill does not access sensitive local files or perform network requests. It operates as a knowledge-based assistant for database query analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM